Association for the Advancement of Artificial Intelligence: AAAI Publications
Not a member yet
26155 research outputs found
Sort by
Evaluating the Synergistic Impact of Fine-Tuning and Retrieval-Augmented Encoding on Enhancing Appendicitis Diagnosis from Limited HPI Notes
No full textThis study explores the impact of fine-tuning combined with a retrieval-augmented encoding approach on encoder language model-generated embeddings for appendicitis diagnosis tasks using patients’ History of Present Illness notes, leading to significantly enhanced diagnostic performance
A Multimodal Fusion Model for Enhanced Industrial Glove-Wearing Compliance Detection
No full textGlove detection in manufacturing environments is challenging due to glove-background blending and limited dataset diversity. To address this, we propose a multimodal detection framework that enhances segmentation models through wrist keypoint-guided feature fusion, effectively reducing false negatives. We also introduce a unified dataset spanning five manufacturing domains to improve generalizability. Experimental results show our method achieves mAP 0.821, outperforming the baseline YOLOv11-Seg (mAP 0.792). This highlights the effectiveness of feature fusion between segmentation and keypoints for accurate and reliable glove compliance monitoring in industrial settings
Beyond Rule-Based Context Awareness: Large Language Models as Adaptive Cognitive Layers in Cyber-Physical Systems
No full textCyber-physical systems (CPS) have traditionally relied on rule-based mechanisms and machine learning models for context awareness. However, these approaches often struggle with dynamic adaptation, multimodal data integration, and real-time decision-making in complex environments. With the emergence of large language models (LLMs), we argue that CPS should adopt LLMs as adaptive cognitive layers capable of interpreting, reasoning, and responding to real-world contexts in real time. This position paper explores the paradigm shift introduced by LLMs, discusses their advantages and limitations, and presents a vision for their integration into next-generation CPS
Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding
No full textDecoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across individuals has prompted the development of deep learning models tailored to each subject. The personalization limits the broader applicability of brain visual decoding in real-world scenarios. To address this issue, we introduce Wills Aligner, a novel approach designed to achieve multi-subject collaborative brain visual decoding. Wills Aligner begins by aligning the fMRI data from different subjects at the anatomical level. It then employs delicate mixture-of-brain-expert adapters and a meta-learning strategy to account for individual fMRI pattern differences. Additionally, Wills Aligner leverages the semantic relation of visual stimuli to guide the learning of inter-subject commonality, enabling visual decoding for each subject to draw insights from other subjects' data. We rigorously evaluate our Wills Aligner across various visual decoding tasks, including classification, cross-modal retrieval, and image reconstruction. The experimental results demonstrate that Wills Aligner achieves promising performance
Interpretable Solutions for Multi-Physics PDEs Using T-NNGP
No full textMultiphysics simulation aims to predict and understand interactions between multiple physical phenomena, aiding in comprehending natural processes and guiding engineering design. The system of Partial Differential Equations (PDEs) is crucial for representing these physical fields, and solving these PDEs is fundamental to such simulations. However, current methods primarily yield numerical outputs, limiting interpretability and generalizability. We introduce T-NNGP, a hybrid genetic programming algorithm that integrates traditional numerical methods with deep learning to derive approximate symbolic expressions for multiple unknown functions within a system of PDEs. T-NNGP initially obtains numerical solutions using traditional methods, then generates candidate symbolic expressions via deep reinforcement learning, and finally optimizes these expressions using genetic programming. Furthermore, a universal decoupling strategy guides the search direction and addresses coupling problems, thereby accelerating the search process. Experimental results on three types of PDEs demonstrate that our method can reliably obtain human-understandable symbolic expressions that fit both the PDEs and the numerical solutions from traditional methods. This work advances multiphysics simulation by enhancing our ability to derive approximate symbolic solutions for PDEs, thereby improving our understanding of complex physical phenomena
AnchorInv: Few-Shot Class-Incremental Learning of Physiological Signals via Feature Space-Guided Inversion
No full textDeep learning models have demonstrated exceptional performance in a variety of real-world applications. These successes are often attributed to strong base models that can generalize to novel tasks with limited supporting data while keeping prior knowledge intact. However, these impressive results are based on the availability of a large amount of high-quality data, which is often lacking in specialized biomedical applications. In such fields, models are often developed with limited data that arrive incrementally with novel categories. This requires the model to adapt to new information while preserving existing knowledge. Few-Shot Class-Incremental Learning (FSCIL) methods offer a promising approach to addressing these challenges, but they also depend on strong base models that face the same aforementioned limitations. To overcome these constraints, we propose AnchorInv following the straightforward and efficient buffer-replay strategy. Instead of selecting and storing raw data, AnchorInv generates synthetic samples guided by anchor points in the feature space. This approach protects privacy and regularizes the model for adaptation. When evaluated on three public physiological time series datasets, AnchorInv exhibits efficient knowledge forgetting prevention and improved adaptation to novel classes, surpassing state-of-the-art baselines
CognitionCapturer: Decoding Visual Stimuli from Human EEG Signal with Multimodal Information
No full textElectroencephalogram (EEG) signals have attracted significant attention from researchers due to their non-invasive nature and high temporal sensitivity in decoding visual stimuli. However, most recent studies have focused solely on the relationship between EEG and image data pairs, neglecting the valuable "beyond-image-modality" information embedded in EEG signals. This results in the loss of critical multimodal information in EEG. To address the limitation, this paper proposes a unified framework that fully leverages multimodal data to represent EEG signals, named CognitionCapturer. Specifically, CognitionCapturer trains modality expert encoders for each modality to extract cross-modal information from the EEG modality. Then, it introduces a diffusion prior to map the EEG embedding space to the CLIP embedding space, followed by using a pretrained generative model, the proposed framework can reconstruct visual stimuli with high semantic and structural fidelity. Notably, the framework does not require any fine-tuning of the generative models and can be extended to incorporate more modalities. Through extensive experiments, we demonstrate that CognitionCapturer outperforms state-of-the-art methods both qualitatively and quantitatively
Argumentative Large Language Models for Explainable and Contestable Claim Verification
No full textThe profusion of knowledge encoded in large language models (LLMs) and their ability to apply this knowledge zero-shot in a range of settings makes them promising candidates for use in decision-making. However, they are currently limited by their inability to provide outputs which can be faithfully explained and effectively contested to correct mistakes. In this paper, we attempt to reconcile these strengths and weaknesses by introducing argumentative LLMs (ArgLLMs), a method for augmenting LLMs with argumentative reasoning. Concretely, ArgLLMs construct argumentation frameworks, which then serve as the basis for formal reasoning in support of decision-making. The interpretable nature of these argumentation frameworks and formal reasoning means that any decision made by ArgLLMs may be explained and contested. We evaluate ArgLLMs’ performance experimentally in comparison with state-of-the-art techniques, in the context of the decision-making task of claim verification. We also define novel properties to characterise contestability and assess ArgLLMs formally in terms of these properties
Hybrid Reasoning About Relative Position and Orientation of Objects and Navigating Agents Using Answer Set Programming
No full textWe study reasoning about relative position, orientation and distance of moving objects in 2D space. We first construct a new hybrid calculus HOPA by augmenting qualitative distance and quantitative constraints into Oriented Point Relation Algebra (OPRA). Then we develop a framework for consistency checking and reasoning with HOPA using Answer Set Programming. This framework can also explain the source of inconsistency, infer new knowledge and generate a layout of objects and their orientation in the discrete space. The framework is capable of reasoning with (un)certain, heterogenous and presumed information. We evaluate efficiency and scalability of our method by computational experiments, and illustrate its applications with sample scenarios from robotic perception and marine navigation
Probabilistic Strategy Logic with Degrees of Observability
No full textThere has been considerable work on reasoning about the strategic ability of agents under imperfect information. However, existing logics such as Probabilistic Strategy Logic are unable to express properties relating to information transparency. Information transparency concerns the extent to which agents' behaviours and actions are observable by other agents. Reasoning about information transparency is useful in many domains including security, privacy, and decision-making. In this paper, we present a formal framework for reasoning about information transparency properties in stochastic multi-agent systems. We extend Probabilistic Strategy Logic with new observability operators that capture the degree of observability of temporal properties by agents. We show that the model checking problem for the resulting logic is decidable